modelscope / modelscope/DiffSynth-Studio
timestep的正余弦编码问题
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
https://github.com/modelscope/DiffSynth-Studio/blob/main/diffsynth/models/qwen_image_dit.py#L414
这里为什么把scale的数值设置成1000，是不是太大了， 一般比如sd3只设置成默认的1啊？
https://github.com/modelscope/DiffSynth-Studio/blob/main/diffsynth/models/sd3_dit.py#L346
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the timestep encoding at diffsynth/models/qwen_image_dit.py#L414 and compare it with the corresponding implementation at diffsynth/models/sd3_dit.py#L346. Determine whether the scale value of 1000 is intentional and what effect changing it would have; the issue is complete when the choice is justified or the needed change is clearly identified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100